INDEX

Explanations

elements related to software features and functionality

oai_token-act-pair · gpt-4o-mini Triggered by @bot

preceding specific units of measure

np_acts-logits-general · gemini-2.0-flash

words for description and statistics

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Zwecke

-0.34

 Punkten

-0.28

 they

-0.27

 suceso

-0.27

 this

-0.27

 Richtung

-0.27

 reasons

-0.26

 metu

-0.26

 solche

-0.26

reasons

-0.25

POSITIVE LOGITS

rungsseite

0.90

tagHelperRunner

0.81

 '\\;'

0.81

 nahilalakip

0.80

MessageTagHelper

0.79

 kaarangay

0.75

 pinulongan

0.75

OGND

0.72

aarrggbb

0.71

 ivelany

0.71

Activations Density 0.584%

elements related to software features and functionality

preceding specific units of measure

words for description and statistics

No Comments

No Known Activations